论文标题
多任务学习以了解视觉场景
Multi-Task Learning for Visual Scene Understanding
论文作者
论文摘要
尽管深度学习最近取得了进展，但大多数方法仍然采用类似孤岛的解决方案，重点是孤立地学习每个任务：为每个任务培训一个单独的神经网络。但是，许多现实世界中的问题都要求采用多模式的方法，因此，用于多任务模型。多任务学习（MTL）旨在利用跨任务的有用信息来提高模型的概括能力。本论文与计算机视觉背景下的多任务学习有关。首先，我们回顾了MTL的现有方法。接下来，我们提出了几种解决多任务学习重要方面的方法。提出的方法在各种基准上进行评估。结果表明，多任务学习的最新技术进展。最后，我们讨论了未来工作的几种可能性。
Despite the recent progress in deep learning, most approaches still go for a silo-like solution, focusing on learning each task in isolation: training a separate neural network for each individual task. Many real-world problems, however, call for a multi-modal approach and, therefore, for multi-tasking models. Multi-task learning (MTL) aims to leverage useful information across tasks to improve the generalization capability of a model. This thesis is concerned with multi-task learning in the context of computer vision. First, we review existing approaches for MTL. Next, we propose several methods that tackle important aspects of multi-task learning. The proposed methods are evaluated on various benchmarks. The results show several advances in the state-of-the-art of multi-task learning. Finally, we discuss several possibilities for future work.
